{"id":"W2963388106","doi":"10.1609/aaai.v33i01.33015797","title":"QUOTA: The Quantile Option Architecture for Reinforcement Learning","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Quantile; Reinforcement learning; Architecture; Computer science; Optimism; Value (mathematics); Artificial intelligence; Econometrics; Machine learning; Economics; Psychology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007923636,0.0002310022,0.0002400266,0.0001002296,0.0003413317,0.00036336,0.00238043,0.00008854191,0.00005322838],"category_scores_gemma":[0.0004894006,0.0001429722,0.0001742492,0.0004605703,0.0001600502,0.0003216503,0.0004465134,0.0004944683,0.0001522021],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005225942,"about_ca_system_score_gemma":0.00008114483,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001738312,"about_ca_topic_score_gemma":0.000002069934,"domain_scores_codex":[0.9979764,0.00002322944,0.0005413907,0.0004356984,0.0006117371,0.000411533],"domain_scores_gemma":[0.9982339,0.0002019663,0.0005587248,0.0004157069,0.0005355528,0.00005415681],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003554775,0.00001652103,0.0001252654,0.00004546625,0.00001428583,3.752374e-8,0.001167783,0.3084116,0.0125185,0.6661253,0.00007601448,0.01146369],"study_design_scores_gemma":[0.00004721397,0.0005169294,0.00009017536,0.0001814299,0.00001290791,0.000002654572,0.0005864401,0.8548919,0.1123662,0.02937516,0.001720333,0.0002087231],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03267565,0.0000126244,0.9510278,0.004615526,0.0007694854,0.001347998,6.678984e-7,0.0001180545,0.009432181],"genre_scores_gemma":[0.9933206,0.00001980644,0.003917509,0.0002530729,0.00007235236,0.00005532693,9.875596e-7,0.00001539184,0.002344897],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.960645,"threshold_uncertainty_score":0.5830239,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05244733210608453,"score_gpt":0.2880631182674069,"score_spread":0.2356157861613223,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}